High-resolution violin transcription using weak labels

Mostra el registre complet Registre parcial de l'ítem

  • dc.contributor.author Tamer, Nazif Can
  • dc.contributor.author Özer, Yigitcan
  • dc.contributor.author Müller, Meinard
  • dc.contributor.author Serra, Xavier
  • dc.date.accessioned 2023-10-24T12:12:12Z
  • dc.date.available 2023-10-24T12:12:12Z
  • dc.date.issued 2023-10-24
  • dc.description This work has been accepted at the 24th International Society for Music Information Retrieval Conference (ISMIR 2023), at Milan, Italy. October 5-9, 2023.
  • dc.description.abstract A descriptive transcription of a violin performance requires detecting not only the notes but also the fine-grained pitch variations, such as vibrato. Most existing deep learning methods for music transcription do not capture these variations and often need frame-level annotations, which are scarce for the violin. In this paper, we propose a novel method for high-resolution violin transcription that can leverage piece-level weak labels for training. Our conformer-based model works on the raw audio waveform and transcribes violin notes and their corresponding pitch deviations with 5.8 ms frame resolution and 10-cent frequency resolution. We demonstrate that our method (1) outperforms generic systems in the proxy tasks of violin transcription and pitch estimation, and (2) can automatically generate new training labels by aligning its feature representations with unseen scores. We share our model along with 34 hours of score-aligned solo violin performance dataset, notably including the 24 Paganini Caprices.ca
  • dc.description.sponsorship This research is funded by the project Musical AI- PID2019-111403GB-I00/AEI/10.13039/501100011033 funded by the Spanish Ministerio de Ciencia, Innovación y Universidades (MCIU) and the Agencia Estatal de Investigación (AEI), and by the German Research Foundation(DFG MU 2686/10-2).
  • dc.format.mimetype application/pdf*
  • dc.identifier.uri http://hdl.handle.net/10230/58121
  • dc.language.iso engca
  • dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/PID2019-111403GB-I00
  • dc.rights © Nazif Can Tamer, Yigitcan Özer, Meinard Müller, Xavier Serra. Licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).ca
  • dc.rights.accessRights info:eu-repo/semantics/openAccessca
  • dc.rights.uri https://creativecommons.org/licenses/by/4.0/ca
  • dc.title High-resolution violin transcription using weak labelsca
  • dc.type info:eu-repo/semantics/preprintca
  • dc.type.version info:eu-repo/semantics/submittedVersionca

Col·leccions

Informes (Departament de Tecnologies de la Informació i les Comunicacions)